The Recurring--and Misleading--Focus on Party Identification [Gallup says we are full of crap]

Gallup ^ | 9/27/12 | Gallup's Editor in Chief

[SoFloFreeper]

The discussion of the party identification composition of poll samples comes up in every presidential election with which I've been involved. Interested observers often opine that when a given poll shows that Candidate X is ahead, it cannot be correct because there is a higher percentage of voters who identify with Candidate X’s party in the sample than there should be, based on comparison to some previous standard.

There are several reasons why this is a faulty approach to evaluating a poll's results.

Party identification is basically an attitudinal variable, not a stable population parameter...

Party identification changes as political tides change.

[SoFloFreeper]

"...it would not be surprising to find that if Barack Obama is enjoying a surge in popularity in any given state, that surge will show up on the ballot question, on his job approval measure, and on the measure of party identification."

In other words, Obamugabe is now wildly popular in all the battleground states and you conservatives had better get used to it...of course, nothing substantial in the economy has changed to MAKE him popular, but just trust us.

[SoFloFreeper]

Here is another quote:

Basically, if an observer is concerned about a poll’s results, that observer should skip over the party identification question and just look at the ballot directly. In other words, cut to the chase. Don’t bother with party identification sample numbers. Look directly at the ballot.

For example, we know that in Ohio:

•Obama won by 5 points in 2008
•Bush won by 2 points in 2004
•Bush won by 3 points in 2000

Now if a given poll in Ohio in this election shows Obama with a 10-percentage-point lead, one should just ask, “How likely is it that Obama would be ahead by 10 points if he won by five points in 2008?” — forgetting party identification, which we assume is going to be higher for the Democratic Party if Obama is ahead, anyway. The discussion of the ballot in the context of previous ballots is, in fact, a reasonable discussion. It may be unlikely that Obama will double his margin in 2012 from what occurred in Ohio in 2008. Or maybe not. But the focus should be directly on the ballot, and discussions of reasons why it might be different than one expects should not involve an attempt to explain the results by focusing on changes in party identification — which is basically a tautological argument.

Well, then why have Party Identification at all on the ballot? By the way, this guy is a bit misleading...you CAN know the number of Republicans and Democrats in many states...Florida, for example, has voters register their party or as an Independent.

I think this is a cover-article because people are beginning to smell their love of Obamugabe and aren’t buying into what they’re cooking.

[sergeantdave]

As the lies and propaganda of these left wing rats pile up, we can expect numerous CYA articles using cooked numbers, ridiculous excuses and hilarious pleas to please believe us, for we are not the frauds and crooks we appear to be.

Okey-dokey.

[Ingtar]

This would be why Gallup is near the bottom in accuracy, I suppose.

[Williams]

Their only point is that supposedly party affiliation is decided by the respondents. So more people say they are democrats because more people are voting for Obama.

Then they say you should question the poll results themselves, not the party identification statistics.

Uh Duh, IF the results seem wrong perhaps the party ID breakdowns also are wrong.

Please note also because Obama isn’t ahead nationally, they have all decided to make the news story Ohio, and that’s all that matters. We’ll just pretend Obama leads by 10 in Ohio and we’ll say it so often people will equate it with a national lead.

[LS]

You almost might think that they are starting to get wind of the early voting numbers we’ve been posting and are becoming a little desperate to save their “models.”

[ez]

The wise pollster would first measure enthusiasm, then translate it to a demographic model which would then be applied to the raw results. Why is this so hard to see?

[Troublemaker]

no mention from Gallup regarding Axelrod & Holder’s threats? hmmmmm....

[LS]

But of course Freepers know-—cause we’ve posted the spreadsheets-—that the absentee numbers look like 2010 numbers on steroids. My fave is Franklin Co., which Zero won by 21 points, now has an absolute R lead of 5500 votes. That’s essentially a 22point swing from 08-—but every county we have data for shows significant Dem disintegration and heavy GOP over performance, even Dem-heavy Cuyahoga Co.

[Red Badger]

My theory is that people all across the country are lying their asses off to the pollsters..........................

[txrefugee]

Gallup is the chicken outfit that caved to Axelrod’s threat of a lawsuit if they didn’t report higher numbers for Obama. They had little credibility before. Now they have none. It would be fantastic to see all these Leftist polls go down in flames on election night.

[nhwingut]

Have you ever seen more pollsters come out and be so defensive? Only if you are guilty do you get defensive.

It’s statistically bizarre. If this followed Bin Laden’s kill or something similar, or a huge job number or good economic data, I would understand. But nothing. Things are getting worse. Historically, nothing makes sense.

[nhwingut]

[kidd]

Gallup: "It may be unlikely that Obama will double his margin in 2012 from what occurred in Ohio in 2008. Or maybe not."

Even if I discount the fact that Gallup is ignoring the 2010 elections, his statement is still a big pantload of crap. Maybe? Maybe not? And this is an attempt at an explanation?

Gallup would have more credibility if they simply said, "Eric Holder owns us. Please believe our made-up numbers or he'll sue."

[Perdogg]

I remember in 2008, pollsters were saucing their own models to reflect their perceived opinions that more African-americas would come out.

This article is blatantly intellectually dishonest.

[MNJohnnie]

Well now we know why Gallup ranked number 18 in accuracy in 2008. They use a poor polling methodology and they arrogantly refuse to listen to those who point out their flaws.

[Conservative12345]

WOW... that is an extremely twisted logic here by Gallup and they could not explain anything at the end... They know that extreme overampling of a given party in a poll against their true representation in the electorate is called “Poll cheating” but they are not to say it no matter what...

[neutrality]

I remember when in 2004 liberals where whining about polls oversampling republicans, this discussion happens every election

[JPG]

Gallup statement translation:

Hey, we tried to be honest and aboveboard with our polling, at least for a while, and then... SLAM-BAM! Axelrod was all over us like white on rice; didn't even let us come up for air before threatening lawsuits. So, yah, we've given the Obama campaign what they wanted. Ran polls with '08 models and then boosted the D's even more (even we laughed over how stupid that was). We know we're full of it but them's the breaks.

[Chewbarkah]

Gallup: “We don’t find that party identification is stable enough to be of much use when it comes to comparing sample-to-sample variations, or sample to exit poll differences.”

If Party identification changes constantly, but it tracks with preferences for candidates, etc., how is it that Gallup and most pollsters use guestimates of PARTY IDENTIFICATION to weight their actual poll reponses before declaring the results? His comments make their whole methodology sound as circular and bogus as we all know it is.